From 3c53d0705a0287906b4002cadb62caf50927fd16 Mon Sep 17 00:00:00 2001
From: Katrin <katrinleinweber@MAC.local>
Date: Sat, 20 Sep 2014 19:49:54 +0200
Subject: [PATCH] sort output by revenue & clearer comments

---
 summarize-flattr-reports.R | 36 ++++++++++++++++++++----------------
 1 file changed, 20 insertions(+), 16 deletions(-)

diff --git a/summarize-flattr-reports.R b/summarize-flattr-reports.R
index 7dbfb1f..b495c38 100644
--- a/summarize-flattr-reports.R
+++ b/summarize-flattr-reports.R
@@ -1,12 +1,12 @@
 # Creates Flattr summary from "Monthly Revenue" reports
 # Started by Katrin from the KonScience Podcast in Sept. 2014
 
-# IMPORTANT
-# Adjust folder path that contains all the downloaded .csv files here
-
-path_to_flattr_reports <- "/Users/YOU/Flattr/"
+# IMPORTANT: Adjust folder path that contains all the downloaded .csv files here
 #   Windows: Please use double backslashes like C:\\User\\YOU...
 #   Linux & Mac: /Users/YOU/ can be abbreviated as '~/...'
+path_to_flattr_reports <- "/Users/YOU/Flattr/"
+
+
 
 # saves original working directory and sets new one as provided above
 original_wd <- getwd()
@@ -14,24 +14,24 @@ setwd(path_to_flattr_reports)
 
 # get filenames of Flattr Monthly Revenue CSVs
 Flattr_filenames <- list.files(path_to_flattr_reports,
-                               pattern = "flattr-revenue-[0-9]*.csv" # RegEx learned from http://www.regexr.com/
-                        )
+                               pattern = "flattr-revenue-[0-9]*.csv"
+                               )
 
 # // TODO find easier way to select path, e.g.
 # - auto-use folder where script runs from // TODO adjust ReadMe.md
 # - prompt user for path, all files (file.choose selects only one) or 1st file and find others in same folder // TODO remove original_wd code
 
-# read data from CSVs into dataframe
+# read data from CSVs into data frame
 raw_Flattrs <- do.call("rbind",
                       lapply(Flattr_filenames,
                              read.csv,
-                             sep = ";", # column separator
+                             sep = ";",
                              dec = ",", # convert decimal separator from , to . for following calculations
-                             stringsAsFactors = FALSE
+                             stringsAsFactors = FALSE # 
                              )
                       ) # Function structure learned from https://stat.ethz.ch/pipermail/r-help/2010-October/255593.html
 
-# load plyr package
+# load plyr package for data frame 
 library(plyr)
 
 # summarizes raw data by title, thus accounting for changes in Flattr Thing ID and URLs
@@ -42,14 +42,18 @@ all_Flattrs <- ddply(raw_Flattrs,
                                         na.rm = TRUE), # removes NA / empty data
                      all_revenue = sum(revenue,
                                          na.rm = TRUE)
-                     ) # // TODO sort output
+                     )
+
+# order Flattr Things by revenue 
+ordered_Flattrs <- all_Flattrs[order(all_Flattrs$all_revenue, decreasing = TRUE),]
 
 # exports summary to same folder
-write.table(all_Flattrs,
-            file = "flattr-revenue-summary.csv", # Change only in combination with RegEx pattern "flattr-revenue-[0-9]*.csv" above! If exported file must not be read into Flattr_filenames object.
-            sep = ";", # reset column separator to Flattr default
-            dec = ",", # reset decimal separator to Flattr default
-            row.names = FALSE # 
+write.table(ordered_Flattrs[2:4],
+            file = "flattr-revenue-summary.csv", # Change only in combination with RegEx pattern "flattr-revenue-[0-9]*.csv" above! Summary file must not be inported on next run of script.
+            # restore column and decimal separators to Flattr defaults
+            sep = ";",
+            dec = ",",
+            row.names = FALSE
             )
 
 # restore original working directory